AMGST: Adaptive multi-graph convolution and spatiotemporal attention network for traffic forecasting
PLOS One · 04.06.2026 · 21 (6) · e0342235
DOI: 10.1371/journal.pone.0342235 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.06.2026. Verfasst von Pei Shi und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of IoT Engineering, Wuxi University, Wuxi, China. Hauptthemen laut MEDLINE: Graph Neural Networks, Prediction Algorithms. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Research of Jiangsu Higher Education Institutions of China, Wuxi Municipal Bureau on Science and Technology, Qinglan Project of Jiangsu Province of China.
Abstract (Originalsprache)
Traffic forecasting is crucial for optimizing traffic management and control strategies. As a powerful approach for analyzing and mining graph-structured data, graph convolution has shown great potential in traffic prediction. However, it still struggles to fully capture global spatial correlations and long-term dynamic temporal dependencies inherent in spatiotemporal traffic patterns. Moreover, the quality of the graph structure directly affects the extraction of these correlations. To address these challenges, we propose AMGST, an Adaptive Multi-Graph Convolution and Spatiotemporal Multi-Head Self-Attention Network for traffic forecasting. AMGST integrates an Adaptive Spatiotemporal Embedding (ASTE) generator, a multi-graph diffusion convolution module, and a spatiotemporal attention mechanism. First, dynamic spatiotemporal representations are generated using the ASTE module. Then, the multi-graph diffusion convolution leverages both a maximum mutual information coefficient matrix and an adaptive matrix to extract fine-grained spatial features. A global spatial attention mechanism is applied to capture dynamic spatial correlations, while a temporal attention module models nonlinear temporal dependencies. Experimental results on four public traffic datasets, including both speed and flow measurements, demonstrate that AMGST consistently surpasses the baselines, confirming its effectiveness in providing accurate traffic forecasts.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of IoT Engineering, Wuxi University, Wuxi, China.
- Jiangsu Engineering Research Center of Hyperconvergence application and security of IoT devices, Wuxi, China.
- School of Electronics & Information Engineering, Nanjing University of Information Science & Technology, Nanjing, China.
- Jiangsu Vocational College of Information Technology, Wuxi, Hebei, China.
ORCID-Profile: Lu Zhang
Förderung
- Natural Science Research of Jiangsu Higher Education Institutions of China
- Wuxi Municipal Bureau on Science and Technology
- Qinglan Project of Jiangsu Province of China
Zitieren
APA
Shi, P., Lu, Q., Chen, J., Lv, X., Zhang, L., Kuang, L., & Sun, J. (2026). AMGST: Adaptive multi-graph convolution and spatiotemporal attention network for traffic forecasting. PLOS One, 21(6), e0342235. https://doi.org/10.1371/journal.pone.0342235
Vancouver
Shi P, Lu Q, Chen J, Lv X, Zhang L, Kuang L, et al. AMGST: Adaptive multi-graph convolution and spatiotemporal attention network for traffic forecasting. PLOS One. 2026;21(6):e0342235. doi:10.1371/journal.pone.0342235
BibTeX
@article{Shi2026,
author = {Shi, Pei and Lu, Qixiang and Chen, Jiahui and Lv, Xiaoliu and Zhang, Lu and Kuang, Liang and Sun, Jiadong},
title = {AMGST: Adaptive multi-graph convolution and spatiotemporal attention network for traffic forecasting},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {6},
pages = {e0342235},
doi = {10.1371/journal.pone.0342235}
}
EUVIMED